vtjnash:jn/cmake-all - Branch - OpenMathLib/OpenBLAS

Ensure feature parity for cmake with Makefile

#5582

Comparing

vtjnash:jn/cmake-all

(

ceb544c

) with

develop

(

097d2d9

)

Untouched: 62

Benchmarks

Passed

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

+1%

32.5 µs32.3 µs

test_daxpy[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

27.6 µs27.5 µs

test_dot[100]

benchmark/pybench/benchmarks/bench_blas.py

22.5 µs22.4 µs

test_daxpy[100-s]

benchmark/pybench/benchmarks/bench_blas.py

24.1 µs24 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

32.8 µs32.7 µs

test_nrm2[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

30.4 µs30.3 µs

test_dot[1000]

benchmark/pybench/benchmarks/bench_blas.py

28.5 µs28.4 µs

test_nrm2[1000-dz]

benchmark/pybench/benchmarks/bench_blas.py

35.3 µs35.2 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

24.3 µs24.2 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

42.2 µs42.1 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

40.6 µs40.6 µs

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

25.9 µs25.9 µs

test_nrm2[100-dz]

benchmark/pybench/benchmarks/bench_blas.py

28.8 µs28.7 µs

test_gesdd[mn0-d]

benchmark/pybench/benchmarks/bench_blas.py

120 µs119.8 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

25.1 µs25.1 µs

test_dgemv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

140.8 µs140.7 µs

test_dgemv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

104.1 µs104 µs

test_gemm[100-s]

benchmark/pybench/benchmarks/bench_blas.py

273.2 µs273.1 µs

test_gesv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

256.8 µs256.7 µs

test_gesdd[mn0-s]

benchmark/pybench/benchmarks/bench_blas.py

109.3 µs109.2 µs

test_gesv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

695.7 µs695.6 µs

test_gemm[100-d]

benchmark/pybench/benchmarks/bench_blas.py

471.3 µs471.3 µs

test_gesv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

394.1 µs394 µs

test_dgemv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

231.3 µs231.2 µs

test_dgemv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

13.9 ms13.9 ms

test_gemm[100-c]

benchmark/pybench/benchmarks/bench_blas.py

659.6 µs659.5 µs

test_syrk[100-z]

benchmark/pybench/benchmarks/bench_blas.py

856.6 µs856.5 µs

test_gesv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

93.3 ms93.3 ms

test_dgbmv[1-100-s]

benchmark/pybench/benchmarks/bench_blas.py

37.3 µs37.3 µs

test_dgemv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

149.3 µs149.3 µs

test_dgbmv[1-100-d]

benchmark/pybench/benchmarks/bench_blas.py

37.9 µs37.9 µs

test_nrm2[100-d]

benchmark/pybench/benchmarks/bench_blas.py

38.2 µs38.2 µs

test_dgemv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

7 ms7 ms

test_gemm[100-z]

benchmark/pybench/benchmarks/bench_blas.py

1.2 ms1.2 ms

test_syrk[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

65.4 ms65.4 ms

test_gesdd[mn1-s]

benchmark/pybench/benchmarks/bench_blas.py

65.2 ms65.2 ms

test_syrk[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

227.6 ms227.6 ms

test_gemm[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

117.4 ms117.4 ms

test_syrk[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

476.4 ms476.4 ms

test_gemm[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

426 ms426 ms

test_gesv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

52.6 ms52.6 ms

test_gesv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

188.6 ms188.6 ms

test_gesv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

353.6 ms353.6 ms

test_dgemv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

26.3 ms26.3 ms

test_gemm[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

239.4 ms239.4 ms

test_gesdd[mn1-d]

benchmark/pybench/benchmarks/bench_blas.py

93.8 ms93.8 ms

test_syrk[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

130.4 ms130.4 ms

test_syev[200-d]

benchmark/pybench/benchmarks/bench_blas.py

58.6 ms58.6 ms

test_gemm[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

875.6 ms875.6 ms

test_dgbmv[1-1000-z]

benchmark/pybench/benchmarks/bench_blas.py

118.9 µs118.9 µs

test_dgemv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

14.8 ms14.8 ms

test_syrk[100-s]

benchmark/pybench/benchmarks/bench_blas.py

213.4 µs213.4 µs

test_syrk[100-c]

benchmark/pybench/benchmarks/bench_blas.py

473.7 µs473.7 µs

test_syev[50-s]

benchmark/pybench/benchmarks/bench_blas.py

1.3 ms1.3 ms

test_syrk[100-d]

benchmark/pybench/benchmarks/bench_blas.py

341.2 µs341.2 µs

test_syev[200-s]

benchmark/pybench/benchmarks/bench_blas.py

49.1 ms49.1 ms

test_gesv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

937.9 µs938 µs

test_syev[50-d]

benchmark/pybench/benchmarks/bench_blas.py

1.4 ms1.4 ms

test_dgbmv[1-1000-c]

benchmark/pybench/benchmarks/bench_blas.py

99.4 µs99.5 µs

test_dgbmv[1-1000-d]

benchmark/pybench/benchmarks/bench_blas.py

83.6 µs83.6 µs

test_dgbmv[1-1000-s]

benchmark/pybench/benchmarks/bench_blas.py

74.9 µs75 µs

test_dgbmv[1-100-c]

benchmark/pybench/benchmarks/bench_blas.py

40.3 µs40.4 µs

Commits

Click on a commit to change the comparison range

Base

develop

097d2d9

+0.07%

cmake: add THREAD_TIMEOUT, prevent in-tree builds, fix ARCH handling Changes: - Add THREAD_TIMEOUT option for thread spin-wait timeout configuration - Prevent in-tree builds with clear error message (protects Makefiles) - Fix ARCH variable to not redundantly re-set when user provides it - Remove experimental warning (CMake now has full Makefile.rule parity) All Makefile.rule options are now supported in CMake: | Makefile.rule Option | CMake Equivalent | |-------------------------------|-------------------------------------| | LIBNAMEPREFIX | LIBNAMEPREFIX | | LIBNAMESUFFIX | LIBNAMESUFFIX | | TARGET | TARGET | | DYNAMIC_ARCH | DYNAMIC_ARCH | | DYNAMIC_OLDER | DYNAMIC_OLDER | | BINARY | BINARY | | USE_THREAD | USE_THREAD | | USE_LOCKING | USE_LOCKING | | USE_OPENMP | USE_OPENMP | | OMP_SCHED | OMP_SCHED | | NUM_THREADS | NUM_THREADS | | NUM_PARALLEL | NUM_PARALLEL | | BUFFERSIZE | BUFFERSIZE | | NO_STATIC / NO_SHARED | BUILD_STATIC_LIBS / BUILD_SHARED_LIBS | | NO_CBLAS | BUILD_WITHOUT_CBLAS | | ONLY_CBLAS | ONLY_CBLAS | | NO_LAPACK | BUILD_WITHOUT_LAPACK | | NO_LAPACKE | BUILD_WITHOUT_LAPACKE | | BUILD_LAPACK_DEPRECATED | BUILD_LAPACK_DEPRECATED | | LAPACK_STRLEN | LAPACK_STRLEN | | BUILD_RELAPACK | BUILD_RELAPACK | | RELAPACK_REPLACE | RELAPACK_REPLACE | | USE_SIMPLE_THREADED_LEVEL3 | USE_SIMPLE_THREADED_LEVEL3 | | USE_TLS | USE_TLS | | INTERFACE64 | INTERFACE64 | | NO_WARMUP | NO_WARMUP | | NO_AFFINITY | NO_AFFINITY | | BIGNUMA | BIGNUMA | | EMBEDDED | EMBEDDED | | NO_AVX / NO_AVX2 / NO_AVX512 | NO_AVX / NO_AVX2 / NO_AVX512 | | FUNCTION_PROFILE | FUNCTION_PROFILE | | QUAD_PRECISION | QUAD_PRECISION | | THREAD_TIMEOUT | THREAD_TIMEOUT | | DEVICEDRIVER_ALLOCATION | DEVICEDRIVER_ALLOCATION | | HUGETLB_ALLOCATION | HUGETLB_ALLOCATION | | HUGETLBFILE_ALLOCATION | HUGETLBFILE_ALLOCATION | | CONSISTENT_FPCSR | CONSISTENT_FPCSR | | GEMM_MULTITHREAD_THRESHOLD | GEMM_MULTITHREAD_THRESHOLD | | SANITY_CHECK | SANITY_CHECK | | MAX_STACK_ALLOC | MAX_STACK_ALLOC | | SYMBOLPREFIX / SYMBOLSUFFIX | SYMBOLPREFIX / SYMBOLSUFFIX | | CPP_THREAD_SAFETY_TEST | CPP_THREAD_SAFETY_TEST | | CPP_THREAD_SAFETY_GEMV | CPP_THREAD_SAFETY_GEMV | | BUILD_BFLOAT16 / BUILD_HFLOAT16 | BUILD_BFLOAT16 / BUILD_HFLOAT16 | | BLAS3_MEM_ALLOC_THRESHOLD | BLAS3_MEM_ALLOC_THRESHOLD | | BUILD_SINGLE/DOUBLE/COMPLEX/COMPLEX16 | BUILD_SINGLE/DOUBLE/COMPLEX/COMPLEX16 | | ARM_SOFTFP_ABI | ARM_SOFTFP_ABI | | DEBUG | CMAKE_BUILD_TYPE=Debug | | PREFIX | CMAKE_INSTALL_PREFIX | | HOSTCC | CMake toolchain files | 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

ceb544c

29 days ago

by vtjnash

Home Terms Privacy Docs